Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3358
    Prev
    Next
    INDEX
    Explanations

    elements related to news reporting and media coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after possessives or contractions

    np_acts-logits-general · gemini-2.0-flash

    possessive 's plus name or title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.50
    γραφ
    -0.49
    原始内容存档于
    -0.47
    PagerAdapter
    -0.43
     indirectly
    -0.43
    Occasionally
    -0.43
    oshin
    -0.42
    esModule
    -0.42
     tacit
    -0.42
     secret
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.76
    joining
    0.74
     Joining
    0.73
    tanleria
    0.73
    Joining
    0.70
    StoreMessageInfo
    0.68
    raszamy
    0.66
     joins
    0.65
     joining
    0.65
     Anchor
    0.65
    Activations Density 0.137%

    No Known Activations